Related papers: pEBR: A Probabilistic Approach to Embedding Based …

Enterprises grapple with the significant challenge of managing proprietary unstructured data, hindering efficient information retrieval. This has led to the emergence of AI-driven information retrieval solutions, designed to adeptly extract…

Dense retrieval models use bi-encoder network architectures for learning query and document representations. These representations are often in the form of a vector representation and their similarities are often computed using the dot…

Partially Relevant Video Retrieval (PRVR) aims to retrieve untrimmed videos partially relevant to a given query. The core challenge lies in learning robust query-video alignment against spurious semantic correlations arising from inherent…

Most techniques for explainable machine learning focus on feature attribution, i.e., values are assigned to the features such that their sum equals the prediction. Example attribution is another form of explanation that assigns weights to…

Traditional retrieval methods have been essential for assessing document similarity but struggle with capturing semantic nuances. Despite advancements in latent semantic analysis (LSA) and deep learning, achieving comprehensive semantic…

Human conversations contain many types of information, e.g., knowledge, common sense, and language habits. In this paper, we propose a conversational word embedding method named PR-Embedding, which utilizes the conversation pairs $…

We explore the effectiveness of an LLM-guided query refinement paradigm for extending the usability of embedding models to challenging zero-shot search and classification tasks. Our approach refines the embedding representation of a user…

Hierarchical Navigable Small World (HNSW) is widely adopted for approximate nearest neighbor search (ANNS) for its ability to deliver high recall with low latency on large-scale, high-dimensional embeddings. The exploration factor, commonly…

Person re identification is a challenging retrieval task that requires matching a person's acquired image across non overlapping camera views. In this paper we propose an effective approach that incorporates both the fine and coarse pose…

Associative memory models are content-addressable memory systems fundamental to biological intelligence and are notable for their high interpretability. However, existing models evaluate the quality of retrieval based on proximity, which…

We propose a novel probabilistic dimensionality reduction framework that can naturally integrate the generative model and the locality information of data. Based on this framework, we present a new model, which is able to learn a smooth…

Performing exact posterior inference in complex generative models is often difficult or impossible due to an expensive to evaluate or intractable likelihood function. Approximate Bayesian computation (ABC) is an inference framework that…

At the heart of contemporary recommender systems (RSs) are latent factor models that provide quality recommendation experience to users. These models use embedding vectors, which are typically of a uniform and fixed size, to represent users…

Deep learning based techniques have been recently used with promising results for data integration problems. Some methods directly use pre-trained embeddings that were trained on a large corpus such as Wikipedia. However, they may not…

Candidate retrieval is the first stage in recommendation systems, where a light-weight system is used to retrieve potentially relevant items for an input user. These candidate items are then ranked and pruned in later stages of recommender…

Representing token embeddings as probability distributions over learned manifolds allows for more flexible contextual inference, reducing representational rigidity while enhancing semantic granularity. Comparative evaluations demonstrate…

We consider probabilistic topic models and more recent word embedding techniques from a perspective of learning hidden semantic representations. Inspired by a striking similarity of the two approaches, we merge them and learn probabilistic…

This paper studies the performances of BERT combined with tree structure in short sentence ranking task. In retrieval-based question answering system, we retrieve the most similar question of the query question by ranking all the questions…

Learning the embedding space, where semantically similar objects are located close together and dissimilar objects far apart, is a cornerstone of many computer vision applications. Existing approaches usually learn a single metric in the…

A number of recent studies have started to investigate how speech systems can be trained on untranscribed speech by leveraging accompanying images at training time. Examples of tasks include keyword prediction and within- and across-mode…